{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T05:40:50Z","timestamp":1772775650315,"version":"3.50.1"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030602758","type":"print"},{"value":"9783030602765","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-60276-5_32","type":"book-chapter","created":{"date-parts":[[2020,10,4]],"date-time":"2020-10-04T07:02:44Z","timestamp":1601794964000},"page":"326-335","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Transfer Learning in Speaker\u2019s Age and Gender Recognition"],"prefix":"10.1007","author":[{"given":"Maxim","family":"Markitantov","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., Batliner, A.: The INTERSPEECH 2009 emotion challenge. In: INTERSPEECH 2009, pp. 312\u2013315 (2009)","DOI":"10.21437\/Interspeech.2009-103"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Kaya, H., et al.: Predicting depression and emotions in the cross-roads of cultures, para-linguistics, and non-linguistics. In: Proceedings of International on Audio\/Visual Emotion Challenge and Workshop, pp. 27\u201335 (2019)","DOI":"10.1145\/3347320.3357691"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Schuller, B. et al.: The INTERSPEECH 2010 paralinguistic challenge. In: INTERSPEECH 2010, pp. 2794\u20132797 (2010)","DOI":"10.21437\/Interspeech.2010-739"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Schuller, B. et al.: The INTERSPEECH 2019 computational paralinguistics challenge: Styrian dialects, continuous sleepiness, baby sounds & orca activity. In: INTERSPEECH 2019, pp. 2378\u20132382 (2019)","DOI":"10.21437\/Interspeech.2019-1122"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., Batliner, A., Schiel, F., Krajewski, J.: The INTERSPEECH 2011 speaker state challenge. In: INTERSPEECH 2011, pp. 3201\u20133204 (2011)","DOI":"10.21437\/Interspeech.2011-801"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Schuller, B. et al.: The INTERSPEECH 2017 computational paralinguistics challenge: Addressee, cold & snoring. In: INTERSPEECH 2017, pp. 3442\u20133446 (2017)","DOI":"10.21437\/Interspeech.2017-43"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Schuller, B. et al.: The INTERSPEECH 2020 computational paralinguistics challenge: elderly emotion, breathing & masks. In: INTERSPEECH 2020, p. 5 (2020)","DOI":"10.21437\/Interspeech.2020-0032"},{"issue":"10","key":"32_CR8","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"S Pan","year":"2009","unstructured":"Pan, S., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2009)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Yu, D., Seltzer, M.: Improved bottleneck features using pretrained deep neural networks. In: INTERSPEECH 2011, pp. 237\u2013240 (2011)","DOI":"10.21437\/Interspeech.2011-91"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Dalmia, S., Li, X., Metze, F., Black, A.: Domain robust feature extraction for rapid low resource ASR development. In: Proceedings of IEEE Spoken Language Technology Workshop (SLT), pp. 258\u2013265 (2018)","DOI":"10.1109\/SLT.2018.8639569"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Sainath, T., Mohamed, A., Kingsbury, B., Ramabhadran, B.: Deep convolutional neural networks for LVCSR. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8614\u20138618 (2013)","DOI":"10.1109\/ICASSP.2013.6639347"},{"issue":"1","key":"32_CR12","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"G Dahl","year":"2011","unstructured":"Dahl, G., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30\u201342 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Wang, Y. et al.: Tacotron: towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135, p. 10 (2017)","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Povey, D., Khudanpur, S.: Deep neural network embeddings for text-independent speaker verification. In: INTERSPEECH 2017, pp. 999\u20131003 (2017)","DOI":"10.21437\/Interspeech.2017-620"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-vectors: robust DNN embeddings for speaker recognition. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329\u20135333 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Garcia-Romero, D., Snyder, D., Sell, G., Povey, D., Mccree, A.: Speaker diarization using deep neural network embeddings. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4930\u20134934 (2017)","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Mccree, A., Sell, G., Povey, D., Khudanpur, S.: Spoken language recognition using x-vectors. In: Proceedings of Odyssey, pp. 105\u2013111 (2018)","DOI":"10.21437\/Odyssey.2018-15"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Ghahremani, P., et al.: End-to-end deep neural network age estimation. In: INTERSPEECH 2018, pp. 277\u2013281 (2018)","DOI":"10.21437\/Interspeech.2018-2015"},{"key":"32_CR19","unstructured":"Burkhardt, F., Eckert, M., Johannsen, W., Stegmann, J.: A database of age and gender annotated telephone speech. In: Proceedings of 7th International Conference on Language Resources and Evaluation (LREC), pp. 1562\u20131565 (2010)"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: OpenSMILE \u2013 the Munich versatile and fast open-source audio feature extractor. In: Proceedings of ACM Multimedia International Conference, pp. 1459\u20131462 (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Kockmann, M., Burget, L., Cernock\u00fd, J.: Brno university of technology system for INTERSPEECH 2010 Paralinguistic Challenge. In: INTERSPEECH 2010, pp. 2822\u20132825 (2010)","DOI":"10.21437\/Interspeech.2010-746"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Meinedo, H., Trancoso, I.: Age and gender classification using fusion of acoustic and prosodic features. In: INTERSPEECH 2010, pp. 2818\u20132821 (2010)","DOI":"10.21437\/Interspeech.2010-745"},{"issue":"1","key":"32_CR23","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.csl.2012.01.008","volume":"27","author":"M Li","year":"2013","unstructured":"Li, M., Han, K., Narayanan, S.: Automatic speaker age and gender recognition using acoustic and prosodic level information fusion. Comput. Speech Lang. 27(1), 151\u2013167 (2013)","journal-title":"Comput. Speech Lang."},{"key":"32_CR24","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.compeleceng.2016.06.002","volume":"53","author":"E Y\u00fccesoy","year":"2016","unstructured":"Y\u00fccesoy, E., Nabiyev, V.: A new approach with score-level fusion for the classification of a speaker age and gender. Comput. Electr. Eng. 53, 29\u201339 (2016)","journal-title":"Comput. Electr. Eng."},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Sarma, M., Sarma, K., Goel, K.: Children\u2019s age and gender recognition from raw speech waveform using DNN. In: Proceedings of Advances in Intelligent Computing and Communication (ICAS), pp. 1\u20139 (2020)","DOI":"10.1007\/978-981-15-2774-6_1"},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"Shobaki, K., Hosom, J.: The OGI kids speech corpus and recognizers. In: INTERSPEECH 2000, p. 4 (2000)","DOI":"10.21437\/ICSLP.2000-800"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Martin, A., Greenberg, C.: NIST 2008 speaker recognition evaluation: performance across telephone and room microphone channels. In: INTERSPEECH 2009, pp. 2579\u20132582 (2009)","DOI":"10.1117\/12.822275"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Martin, A., Greenberg, C.: The NIST 2010 speaker recognition evaluation. In: INTERSPEECH 2010, pp. 2726\u20132729 (2010)","DOI":"10.21437\/Interspeech.2010-722"},{"key":"32_CR29","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"32_CR30","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, p. 14 (2014)"},{"key":"32_CR31","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"32_CR33","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. arXiv preprint arXiv: 1905.11946, p. 10 (2019)"},{"key":"32_CR34","doi-asserted-by":"crossref","unstructured":"Zhou, H., Bai, X., Du, J.: An investigation of transfer learning mechanism for acoustic scene classification. In: Proceedings of International Symposium on Chinese Spoken Language Processing (ISCSLP), pp. 404\u2013408 (2018)","DOI":"10.1109\/ISCSLP.2018.8706712"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Tang, D., Zeng, J., Li, M.: An end-to-end deep learning framework for speech emotion recognition of a typical individuals. In: INTERSPEECH 2018, pp. 162\u2013166 (2018)","DOI":"10.21437\/Interspeech.2018-2581"},{"key":"32_CR36","unstructured":"Tripathi, S., Kumar, A., Ramesh, A., Singh, C., Yenigalla, P.: Focal loss based residual convolutional neural network for speech emotion recognition. arXiv preprint arXiv:1906.05682 (2019)"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Hartmann, W., et al.: Improved single system conversational telephone speech recognition with VGG bottleneck features. In: INTERSPEECH 2017, pp. 112\u2013116 (2017)","DOI":"10.21437\/Interspeech.2017-1513"},{"issue":"9","key":"32_CR38","first-page":"8","volume":"7","author":"M Sankupellay","year":"2018","unstructured":"Sankupellay, M., Konovalov, D.: Bird call recognition using deep convolutional neural network, ResNet-50. Acoustics Australia 7(9), 8 (2018)","journal-title":"Acoustics Australia"},{"key":"32_CR39","doi-asserted-by":"crossref","unstructured":"Markitantov, M., Verkholyak, O.: Automatic recognition of speaker age and gender based on deep neural networks. In: Proceedings of International Conference on Speech and Computer (SPECOM), pp. 327\u2013336 (2019)","DOI":"10.1007\/978-3-030-26061-3_34"},{"key":"32_CR40","doi-asserted-by":"crossref","unstructured":"McFee, B. et al.: Librosa: audio and music signal analysis in Python. In: Proceedings of 14th Python in Science Conference, pp. 18\u201324 (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"32_CR41","unstructured":"Paszke, A. et al.: Automatic differentiation in PyTorch. In: Proceedings of Autodiff Workshop of Neural Information Processing Systems (NIPS), p. 4 (2017)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60276-5_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T02:43:59Z","timestamp":1669085039000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-60276-5_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602758","9783030602765"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60276-5_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St. Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"160","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"65","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the Corona pandemic SPECOM 2020 was held as a virtual event","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}